Use module docx to get text from a file with a table

[deanhystad]

This finds tables in a document and converts them to dataframes.

from docx import Document
from docx.document import Document as _Document
from docx.oxml.table import CT_Tbl
from docx.table import _Cell, Table
import pandas as pd

def tables(parent):
    if isinstance(parent, _Document):
        element = parent.element.body
    elif isinstance(parent, _Cell):
        element = parent._tc

    for child in element.iterchildren():
        if isinstance(child, CT_Tbl):
            table = Table(child, parent)
            data = [[cell.text for cell in row.cells] for row in table.rows]
            yield pd.DataFrame(data[1:], columns=data[0])

for table in tables(Document('data.docx')):
    print(table, "\n")

I made a word document with multiple paragraphs and two tables. The output from running the program accurately shows the two tables.

Output:
   A  B  C  D
0  1  3  5  7
1  2  4  6  8 

   A  B  C
0  1  2  3
1  4  5  6